检索结果-内蒙古大学图书馆

IEEE Transactions on Intelligent Vehicles 2024年 1-13页

作者： Cao, Yihong Zhang, Hui Lu, Xiao Xiao, Zheng Yang, Kailun Wang, Yaonan College of Computer Science and Electronic Engineering Hunan University Changsha China National Engineering Research Center of Robot Vision Perception and Control Technology School of Robotics Hunan University Changsha China College of Engineering and Design Hunan Normal University Changsha China

Domain adaptive semantic segmentation enables robust pixel- wise understanding in real-world driving scenes. Source-free domain adaptation, as a more practical technique, addresses the concerns of data privacy and storage limitations in typical unsupervised domain adaptation methods, making it especially relevant in the context of intelligent vehicles. It utilizes a well-trained source model and unlabeled target data to achieve adaptation in the target domain. However, in the absence of source data and target labels, current solutions cannot sufficiently reduce the impact of domain shift and fully leverage the information from the target data. In this paper, we propose an end-to-end source-free domain adaptation semantic segmentation method via Importance-Aware and Prototype-Contrast (IAPC) learning. The proposed IAPC framework effectively extracts domain-invariant knowledge from the well-trained source model and learns domain-specific knowledge from the unlabeled target domain. Specifically, considering the problem of domain shift in the prediction of the target domain by the source model, we put forward an importance-aware mechanism for the biased target prediction probability distribution to extract domain-invariant knowledge from the source model. We further introduce a prototype-contrast strategy, which includes a prototype-symmetric cross-entropy loss and a prototype-enhanced cross-entropy loss, to learn target intra-domain knowledge without relying on labels. A comprehensive variety of experiments on two domain adaptive semantic segmentation benchmarks demonstrates that the proposed end-to-end IAPC solution outperforms existing state-of-the-art methods. The source code is publicly available at https://***/yihong-97/Source-free-IAPC. IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

On Designing Control Systems for Electron-Beam Processing Plants

引用

Russian Electrical engineering 2024年第7期95卷 579-584页

作者： Kozhechenko, A.S. Sliva, A.P. Maslov, A.N. Shcherbakov, A.V. Goncharov, A.L. Rodyakina, R.V. Dragunov, V.K. Department of Power Supply of Industrial Enterprises and Electric Technologies National Research University "Moscow Power Engineering Institute" Moscow111250 Russia Department of Metal Technologies National Research University "Moscow Power Engineering Institute" Moscow111250 Russia Department of Robotics Mechatronics Dynamics and Machine Strength National Research University "Moscow Power Engineering Institute" Moscow111250 Russia

This study shows the need for a common structured approach to designing control systems for electron-beam welding, surfacing, and additive shaping plants. The main controlled parameters of the process are highlighted. The three-level hierarchical structure of the control system is described. The control processes are differentiated taking into account the process requirements for electron-beam treatment processes and the features of the vacuum system, the electron gun, and the positioning system, as well as the system of taking images of the treated area according to the signal of backscattered electrons. The types and quantitative characteristics of the parameters of the signals necessary for running the system are given. It is shown that it is effective to divide the control processes in three groups, depending on the requirements on the rapid response of the actuators, as well as on the need for synchronizing some processes with others over time. The presented differentiation is used to propose a method for selecting technical facilities for each of the mentioned groups. An example is provided of constructing a control system for an electron-beam process plant using hardware components available for purchase. © Allerton Press, Inc. 2024.

关键词： Numerical control systems

来源：评论

学校读者我要写书评

暂无评论

How Evolutionary Algorithms Consume Energy Depending on the Language and Its Level 18th

How Evolutionary Algorithms Consume Energy Depending on the...

引用

18th International Conference on Learning and Intelligent Optimization, LION 2024

作者： Merelo-Guervós, Juan J. García-Valdez, Mario Department of Computer Engineering Automatics and Robotics University of Granada Granada Spain Department of Graduate Studies National Technological Institute of Mexico Tijuana Mexico

ISBN: (纸本)9783031756221

Making evolutionary algorithms greener implies tackling implementation issues from different angles. Practitioners need to focus on those that can be more easily leveraged, such as the choice of the language that is going to be used;high-level (interpreted), mid-level (based on multi-platform virtual machines), and low-level (native) languages will need power in different ways, and choosing one or the other will have an impact on energy consumption. We will be looking at the implementation of key evolutionary algorithm functions, in three languages at three different levels: the high-level JavaScript, the mid-level Kotlin, which runs on the Java Virtual Machine, and the low-level Zig. Looking beyond the obvious, as the lower the level, the less energy consumption should be expected, we will try to have a more holistic view of the implementation of the algorithms in order to extract best practices regarding its green implementation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Ferroelectric composite-based piezoelectric energy harvester for selfpowered detection of obstructive sleep

引用

Journal of Materiomics 2023年第4期9卷 609-617页

作者： Swati Panda Hyoju Shin Sugato Hajra Yumi Oh Wonjeong Oh Jeonghyeon Lee P.M.Rajaitha Basanta Kumar Panigrahi Jyoti Shukla Alok Kumar Sahu Perumal Alagarsamy Hoe Joon Kim Department of Robotics and Mechatronics Engineering Daegu Gyeongbuk Institute of Science and Technology(DGIST)Daegu42988South Korea Department of Electrical Engineering Siksha‘O’Anusandhan UniversityBhubaneswar751030India Department of Electrical Engineering Poornima College of EngineeringJaipur303903India Department of Physics Indian Institute of Technology-GuwahatiAssam781039India Robotics and Mechatronics Research Center Daegu Gyeongbuk Institute of Science and Technology(DGIST)Daegu42988South Korea

Lead-free piezoelectric ceramic is a promising material for energy harvesters,as they have superior electromechanical,ferroelectric,and piezoelectric *** addition,piezoelectric ceramics can be blended with polymer to achieve high-flexibility polymer-ceramic composites,providing mechanical robustness and *** this context,a new lead-free ferroelectric material,having the chemical formula SrTi_(2)O_(5)(STO),was synthesized using a high-temperature solid-state *** analyses of the structural,morphological,and electrical properties of the synthesized material were *** crystallizes with orthorhombic symmetry and space group of *** frequency and temperature-dependent dielectric parameters were evaluated,and impedance spectroscopy shed light on the charge *** PDMS-STO composites at different mass fraction of the STO were prepared using a solvent casting route,and a corresponding piezoelectric nanogenerator(PENG)was *** electrical output of the different PENG by varying massfractions of STO in PDMS and varying force were *** 15%(in mass)PENG device delivered the highest peak-to-peak voltage,current,and power density of 25 V,92 nA,and 0.64 mW@500 MU,*** biomechanical energy harvesting using the PENG device by daily human motions,bending of the device,and attaching the device to laboratory equipment was *** the PENG device was attached to the human throat region,and snoring signals were recorded.A classification model was designed employing the convolutional neural network(CNN)*** have been laid to differentiate between normal and abnormal snores,which could help the patient with screening and early disease detection,contributing to self-powered healthcare applications.

关键词： Lead-free Ferroelectric Nanogenerator Sleepdisorder

来源：评论

学校读者我要写书评

暂无评论

Reply to comment on “Ferroelectric composite-based piezoelectric energy harvester for self-powered detection of obstructive sleep” by A. Tkach and O. Okhay

引用

Journal of Materiomics 2024年第5期10卷 1160-1164页

作者： Swati Panda Hyoju Shin Sugato Hajra Yumi Oh Wonjeong Oh Jeonghyeon Lee P.M.Rajaitha Basanta Kumar Panigrahi Jyoti Shukla Alok Kumar Sahu Perumal Alagarsamy Hoe Joon Kim Department of Robotics and Mechatronics Engineering Daegu Gyeongbuk Institute of Science and Technology(DGIST)Daegu 42988South Korea Department of Electrical Engineering Siksha‘O’Anusandhan UniversityBhubaneswar 751030India Department of Electrical Engineering Poornima College of EngineeringJaipur 303903India Department of Physics Indian Institute of Technology-GuwahatiAssam 781039India Robotics and Mechatronics Research Center Daegu Gyeongbuk Institute of Science and Technology(DGIST)Daegu 42988South Korea

In this contribution,we reply to comments made by Tkach et *** our publication *** 2023;9:*** main interest of our work is to synthesize a lead-free material,SrTi_(2)O_(5)(STO),and then utilize it in the formation of composites and finally design the piezoelectric nanogenerator(PENG)for self-powered sensor *** authors have observed the presence of piezoelectric voltage and current output from the *** authors humbly indicate that the PENG devices were poled using a DC poling setup as conditions mentioned in *** 2023;9:609(Panda et al.,2023)[1].The doping of STO into the PDMS increased from 2% to 20%(in mass).In this process,the piezoelectric output of the PENG device was observed to be highest for 15%(in mass)STO-PDMS ***,we agree with the comment raised by Tkach et al.,and further we have addressed the issues in a step-by-step response as follows.

关键词： Ferroelectric Lead-free Piezoelectric Polycrystalline

来源：评论

学校读者我要写书评

暂无评论

AI-based Restoration Reflection Region Method for 3D Automatic Optical Inspection

引用

Journal of institute of Control, robotics and Systems 2023年第11期29卷 936-944页

作者： Kim, Chan-Hoe Ha, Min-Ho Yun, Sung-Chul Park, Tae-Hyoung Department of Control and Robot Engineering Chungbuk National University Korea Republic of Industrial AI Research Center Chungbuk National University Korea Republic of Department of Intelligent Systems and Robotics Chungbuk National University Korea Republic of

This study focuses on a three-dimensional measurement system of components on a printed-circuit-board (PCB). Most existing methods for automatic optical inspection face the problem of light reflecting on components. We herein propose a new method to restore the reflection area of components with the aim of measuring their shape accurately. This method use a pattern projection system along with an algorithm for restoring the components’ reflection area. For efficient restoration of the restore reflection area, the reflection regions are first identified through pixel resolution, wherein, saturated pixels represent the reflection regions. Then, the PCB components are tilted slightly using solder. These characteristics are used to, obtain the rotation matrix of a component, and its reflection area is restored. The performance of the proposed method is evaluated through a series of experiments, whose. results demonstrate its effectiveness. © ICROS 2023.

关键词： Printed circuit boards

来源：评论

学校读者我要写书评

暂无评论

General Planning Method for Humanoid Collaborative Robots using Large Language Models

General Planning Method for Humanoid Collaborative Robots us...

引用

2024 China Automation Congress, CAC 2024

作者： Gao, Runqin Shi, Jiamin Tian, Shu Chen, Shitao National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China

ISBN: (纸本)9798350368604

Humanoid robots, capable of simulating human behavior and decision-making, have garnered extensive attention due to their anthropomorphic structures and versatile functional designs. Traditionally, actions and high-level decision-making in robots have been manually achieved by developers, requiring modifications and adaptations for different task requirements, thus lacking autonomous decision-making capabilities. With the rapid advancement of deep learning technologies, large language models trained on internet data have provided new solutions for robot intelligence, demonstrating effective applications in high-level task planning for robots. Based on this, we propose a general high-level task planning method using large language models, implemented on a mobile single-arm humanoid robot as the platform. This method consists of two core components: high-level decision planning and low-level action execution, coupled through the robot’s atomic action interface. The robot autonomously completes sequential action planning by receiving natural language task instructions and executes long-term, complex, general indoor collaborative tasks. By deploying on a real robot, we conducted sub-module tests and overall system performance tests, successfully achieving the process of sorting and organizing tasks in an indoor experimental environment. © 2024 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

LSTM with AhI-model based Kalman Filter for Lithium-ion Battery State of Charge Estimation

LSTM with AhI-model based Kalman Filter for Lithium-ion Batt...

引用

2024 China Automation Congress, CAC 2024

作者： Luo, Xiangyong Dang, Lujuan Yang, Meng Chen, Badong National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China

ISBN: (纸本)9798350368604

Accurate state of charge (SOC) estimation of lithium-ion battery in battery management system (BMS) is important for the safety and reliability of electronic devices and electric vehicles. This paper proposes a LSTM-extended Kalman filter based on AhI-model (LSTM-EA), which constrains SOC result from LSTM with an AhI-model based Kalman filter. AhI-model is based on Ampere-hour integration method and requires simpler structure to obtain estimated SOC with higher accuracy and robustness. In the experiments, the public datasets from the center for Advanced Life Cycle engineering (CALCE) are used to validate the SOC estimation performance. The mean absolute error (MAE) and maximum error of the proposed method are less than 2.51% and 8.82% respectively. © 2024 IEEE.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

OCViTnet: Pulse Wave Learning for Cuffless Blood Pressure Estimation of Medical Service Robots

OCViTnet: Pulse Wave Learning for Cuffless Blood Pressure Es...

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Cen, Yuhui Luo, Jingjing Wang, Hongbo Chen, Li Zhu, Xing Luo, Jingchun Fudan University Human Phenome Institute Shanghai200433 China Fudan University The Institute of Ai and Robotics Academy for Engineering and Technology China Engineering Research Center of Ai & Robotics Ministry of Education Shanghai210043 China

ISBN: (纸本)9798350325706

Blood pressure (BP) estimation through cuffless approaches is gaining prominence in precision healthcare, and the emergence of robotic medical services adds impetus to this trend with enhanced diagnostic capabilities. In our endeavor to enable medical service robots for cuffless BP self-estimation, we propose OCViTnet, a deep-learning network model grounded in pulse wave analysis (PWA). The model introduces a novel waveform processing architecture: an omni-scale convolution subnet captures single-period waveform characteristics, the Vision Transformer subnet extracts multi-period waveform features, and a regressor fuses phenotypic information with pulse wave features and performs BP regression. Experimental results perform exceptionally well in non-contact BP estimation from forehead imaging photoplethysmography. Additionally, this paper pioneers the utilization of the radial artery pulse wave for BP estimation. Leveraging the British Hypertension Society standard, our approach yields notable results, assessing the pulse diagnosis robot's BP estimation performance at grade C/B (systolic/diastolic BP). This effort advances the potential of cuffless BP estimation in pulse diagnosis robotics and underscores the practical viability of our proposed intelligent methodology based on PWA. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Submegahertz Nucleation of Plasmonic Vapor Microbubbles near a Solid Vertical Boundary

引用

Physical Review Letters 2024年第6期133卷 064001-064001页

作者： Fulong Wang (王福龙) Zhibin Hu Binglin Zeng Chenliang Xia Lihua Dong Huimin Wang Lijun Yang Yuliang Wang (王玉亮) Robotics Institute School of Mechanical Engineering and Automation National Center for Materials Service Safety School of Astronautics Ningbo Institute of Technology

Laser triggered and photothermally induced vapor bubbles have emerged as promising approaches to facilitate optomechanical energy conversion for numerous applications in microfluidics and nanofluidics. Here, we report an observation of spontaneously triggered periodic nucleation of plasmonic vapor bubbles near a rigid sidewall with readily tuned nucleation frequency from 0.8 kHz to over 200 kHz. The detailed collapsing process of the vapor bubbles was experimentally and numerically investigated. We find that the lateral migration of residual bubbles toward the sidewall refreshes the laser spot area, terminates the subsequent steady bubble growth, and leads to the repeatable bubble nucleation. A mathematic model regarding the Kelvin impulses was derived. It shows that the competition between the rigid boundary induced Bjerknes force and laser irradiation caused thermal Marangoni force on collapsing bubbles governs the process. The model also leads to a criterion of γζ<0.34 for repeatable bubble nucleation, where γ is the normalized distance and ζ thermal Marangoni coefficient. This study demonstrates nucleation of violent vapor bubbles at extreme high frequencies, providing an approach to remotely realize strong localized flows in microfluidics and nanofluidics.

关键词： Bubble dynamics Drop or bubble formation Drops & bubbles Laser-induced cavitation Lasers Metals Microfluidic devices Nanofluidic devices Nanoparticles Water

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：